Scholarlink

<p>Cloud computing provides a flexible and scalable infrastructure for storing and processing heterogeneous data types, ranging from general information to highly sensitive datasets. In healthcare environments, where data includes personally identifiable information, clinical diagnostics, and treatment outcomes, ensuring secure and privacy-preserving data sharing over cloud platforms remains a critical and complex challenge. Hence, it is important to protect the patients’ information with more data privacy and high security. The proposed approach utilizes an advanced Score, Arrange, and Cluster k-anonymization technique, which ensures robust data anonymization by making it difficult to identify specific individuals within the dataset. To further secure the anonymized data, the DNA-based Genetic Algorithm encryption method is applied, providing an additional layer of protection. The optimization process is guided by the African Vultures Optimization Algorithm, enhanced with Simulated Annealing, to improve the efficiency of anonymization while minimizing the information loss. The results demonstrate that the proposed technique effectively protects the privacy of medical databases.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Privacy-preserving data publishing in cloud computing using a genetic-African vultures optimization-based enhanced data anonymization framework

  • 期刊论文

  • 发表日期：

    2026年1月13日

查看全文
  • R. Sahana Lokesh

摘要

Cloud computing provides a flexible and scalable infrastructure for storing and processing heterogeneous data types, ranging from general information to highly sensitive datasets. In healthcare environments, where data includes personally identifiable information, clinical diagnostics, and treatment outcomes, ensuring secure and privacy-preserving data sharing over cloud platforms remains a critical and complex challenge. Hence, it is important to protect the patients’ information with more data privacy and high security. The proposed approach utilizes an advanced Score, Arrange, and Cluster k-anonymization technique, which ensures robust data anonymization by making it difficult to identify specific individuals within the dataset. To further secure the anonymized data, the DNA-based Genetic Algorithm encryption method is applied, providing an additional layer of protection. The optimization process is guided by the African Vultures Optimization Algorithm, enhanced with Simulated Annealing, to improve the efficiency of anonymization while minimizing the information loss. The results demonstrate that the proposed technique effectively protects the privacy of medical databases.